© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 6297
    Prev
    Next
    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deadly
    -0.07
    �s
    -0.06
     ipsum
    -0.06
     untuk
    -0.06
     impacts
    -0.06
     والد
    -0.06
     feasibility
    -0.06
     před
    -0.06
     день
    -0.06
    ächst
    -0.06
    POSITIVE LOGITS
    _REL
    0.08
    Dup
    0.07
    .SelectCommand
    0.07
    .CO
    0.07
    spec
    0.07
    ορειο
    0.06
    ırken
    0.06
    BILL
    0.06
    dev
    0.06
    анс
    0.06
    Activations Density 0.694%

    No Known Activations